Triple
T22308716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple A7 |
E551454
|
entity |
| Predicate | level1Cache |
P20331
|
FINISHED |
| Object | 64 KB instruction cache per core |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 64 KB instruction cache per core | Statement: [Apple A7, level1Cache, 64 KB instruction cache per core]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: level1Cache Context triple: [Apple A7, level1Cache, 64 KB instruction cache per core]
-
A.
level1Feature
chosen
Indicates that one entity possesses or is associated with a primary or first-tier feature of another entity.
-
B.
lowerLevelUsedFor
Indicates that a lower-level component, resource, or abstraction is utilized to implement, support, or realize the functionality of a higher-level one.
-
C.
levelServed
Indicates that a particular service, function, or resource is provided or made available at a specified level or tier.
-
D.
cellLevels
Indicates a relationship where specific levels or layers within a cell (or cellular structure) are identified, characterized, or associated with another entity.
-
E.
meetsAtLevel
Indicates that two or more entities encounter or interact with each other at a specific hierarchical, structural, or progression level.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1574c8a248190bf5eef5be78381fd |
completed | April 29, 2026, 12:56 a.m. |
| PD | Predicate disambiguation | batch_69e72ffa438481908f80879aef2a589b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:42 p.m.